Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4874 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8489. Min Act: -0.0000

Data Index: 373838 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8700. Min Act: 0.0000

Data Index: 913397 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7092. Min Act: -0.0000

Data Index: 741737 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6290. Min Act: 0.0001

Data Index: 1155990 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6741. Min Act: -0.0000

Data Index: 490023 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1356289 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1054862 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5603. Min Act: -0.0000

Data Index: 748845 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5729. Min Act: 0.0000

Data Index: 993361 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5698. Min Act: -0.0000

Data Index: 396039 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5765. Min Act: -0.0000

Data Index: 969444 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5436. Min Act: 0.0000

Data Index: 774857 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5386. Min Act: -0.0000

Data Index: 483307 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5569. Min Act: 0.0000

Data Index: 116605 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5372. Min Act: -0.0000

Data Index: 362638 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5422. Min Act: -0.0000

Data Index: 415133 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1275489 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1173810 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1177776 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1220256 (C4 (Web Text))

Max Activating Token Index: 738